Advanced search


Knowledge area




519 results, page 1 of 10

Detección de comportamiento no verbal en interacción humano-robot

Detection of non-verbal behavior in human-robot interaction

Ernesto Adrián Lozano De la Parra (2023)

La comunicación no verbal desempeña un papel vital en la interacción humana. En el contexto de la interacción humano-robot (IHR), los robots sociales están diseñados principalmente para la comunicación verbal con los humanos, dejando a la comunicación no verbal como un área de investigación abierta. En este trabajo, se presenta una arquitectura flexible y abierta llamada Software Arquitechture for Nonverbal Interaction in Human-Robot Interaction (SANI-HRI) diseñada para facilitar las interacciones no verbales en IHR. Entre sus componentes se encuentra un Cuaderno Computacional P2P basado en navegador web, aprovechado para codificar, ejecutar y compartir programas reactivos. Pueden incluirse modelos de aprendizaje automático para el reconocimiento en tiempo real de gestos, poses y estados de ´animo, empleando protocolos como MQTT. Otro componente clave es un Broker para distribuir datos entre distintos dispositivos físicos, como robots, dispositivos vestibles y sensores ambientales, así como modelos de aprendizaje automático que comprendan diferentes tipos de datos. Se demuestra la utilidad de esta arquitectura mediante tres escenarios de interacción: (i) el primero que emplea la proxémica y la dirección de la mirada para iniciar un encuentro improvisado, (ii) un segundo que utiliza técnicas de visión por computadora para detectar y analizar expresiones faciales y corporales, así como el uso sensores biométricos para obtener datos de ritmo cardiaco durante una rutina de ejercicio, y (iii) un tercero que incorpora el reconocimiento de objetos y Modelos de Lenguaje Grandes para sugerir comidas a cocinar en función de los ingredientes disponibles. Estos escenarios ilustran cómo los componentes de la arquitectura pueden integrarse para abordar nuevos escenarios, en los que los robots necesitan inferir señales no verbales de los usuarios.

Nonverbal communication plays a vital role in human interaction. In the context of Human-Robot Interaction (HRI), social robots are designed primarily for verbal-based communication with humans, making nonverbal communication an open research area. We present a flexible, open framework called Software Architecture for Nonverbal Interaction in Human-Robot Interaction (SANI-HRI) designed to facilitate nonverbal interactions in HRI. Among its components it has a P2P Browser-Based Computational Notebook, leveraged to code, run, and share reactive programs. Machine-learning models can be included for real-time recognition of gestures, poses, and moods, employing protocols such as MQTT. Another key component is a broker for distributing data among different physical devices like the robot, wearables, and environmental sensors and also machine learning models. We demonstrate this framework’s utility through three interaction scenarios: (i) the first one employing proxemics and gaze direction to initiate an impromptu encounter, (ii) a second that uses computer vision techniques to detect and analyze facial and body expressions, as well as the use of biometric sensors to obtain heart rate data during a workout routine, and (iii) a third one incorporating object recognition and a Large-Language Model to suggest meals to be cooked based on available ingredients. These scenarios illustrate how the framework’s components can be seamlessly integrated to address new scenarios, where robots need to infer nonverbal cues from users.

Master thesis

Interacción humano-robot, Comunicación no verbal, Broker MQTT, Notebook computacional, Modelos linguísticos grandes, SANI-HRI Human-robot interaction, Nonverbal communication, Broker MQTT, Computational notebook, Large language models, SANI-HRI INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES SISTEMAS DE RECONOCIMIENTO DE CARACTERES SISTEMAS DE RECONOCIMIENTO DE CARACTERES

Pautas de referencia para el desarrollo del impuesto especial sobre el uso de inteligencia artificial y robótica en México

Kharem Deyanira Omaña Pérez (2023)

Las tecnologías disruptivas como la inteligencia artificial y la robótica, representan un reto para los sistemas tributarios actuales, múltiples líneas de investigación señalan la necesidad de gravar la robótica con la finalidad de compensar el detrimento que ésta genera en la sociedad por el desplazamiento laboral. Este artículo tiene la finalidad de analizar los

elementos necesarios para el desarrollo de un impuesto especial sobre el uso de inteligencia artificial y robótica en México. Es importante mencionar que para desarrollar las ideas que sustentan este estudio se hizo uso de la metodología de investigación documental y analítica, la metodología del derecho comparado, con apoyo del método inductivo y deductivo. Derivado de lo anterior podemos encontrar que nuestro país tiene un contexto histórico, cultural y económico

particular donde es necesario aplicar un impuesto a los robots con la finalidad de situar a México en la economía del conocimiento. Sin embargo, dicha medida genera diversas dificultades jurídicas que serán expuestas para generar certeza sobre la legalidad de establecer el gravamen que se propone. Finalmente, se concluye que este fenómeno

requiere de acciones inmediatas no solo en el ámbito jurídico sino en la implementación de políticas públicas por parte del Estado con el objeto de generar bienestar social en la población y abrazar el fenómeno de las tecnologías como la inteligencia artificial y la robótica.

Other

Master Degree Work

Inteligencia Artificial Robótica Desplazamiento laboral Economía del conocimiento INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS CIENCIAS TECNOLÓGICAS

Optimizing nitrogen fertilizer and planting density levels for maize production under current climate conditions in Northwest Ethiopian midlands

Kindie Tesfaye Dereje Ademe Enyew Adgo (2023)

This study determined the most effective plating density (PD) and nitrogen (N) fertilizer rate for well-adapted BH540 medium-maturing maize cultivars for current climate condition in north west Ethiopia midlands. The Decision Support System for Agrotechnology Transfer (DSSAT)-Crop Environment Resource Synthesis (CERES)-Maize model has been utilized to determine the appropriate PD and N-fertilizer rate. An experimental study of PD (55,555, 62500, and 76,900 plants ha−1) and N (138, 207, and 276 kg N ha−1) levels was conducted for 3 years at 4 distinct sites. The DSSAT-CERES-Maize model was calibrated using climate data from 1987 to 2018, physicochemical soil profiling data (wilting point, field capacity, saturation, saturated hydraulic conductivity, root growth factor, bulk density, soil texture, organic carbon, total nitrogen; and soil pH), and agronomic management data from the experiment. After calibration, the DSSAT-CERES-Maize model was able to simulate the phenology and growth parameters of maize in the evaluation data set. The results from analysis of variance revealed that the maximum observed and simulated grain yield, biomass, and leaf area index were recorded from 276 kg N ha−1 and 76,900 plants ha−1 for the BH540 maize variety under the current climate condition. The application of 76,900 plants ha−1 combined with 276 kg N ha−1 significantly increased observed and simulated yield by 25% and 15%, respectively, compared with recommendation. Finally, future research on different N and PD levels in various agroecological zones with different varieties of mature maize types could be conducted for the current and future climate periods.

Article

Maize Model Planting Density CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MAIZE MODELS SPACING NITROGEN FERTILIZERS YIELDS

Using an incomplete block design to allocate lines to environments improves sparse genome-based prediction in plant breeding

Osval Antonio Montesinos-Lopez ABELARDO MONTESINOS LOPEZ RICARDO ACOSTA DIAZ Rajeev Varshney Jose Crossa ALISON BENTLEY (2022)

Genomic selection (GS) is a predictive methodology that trains statistical machine-learning models with a reference population that is used to perform genome-enabled predictions of new lines. In plant breeding, it has the potential to increase the speed and reduce the cost of selection. However, to optimize resources, sparse testing methods have been proposed. A common approach is to guarantee a proportion of nonoverlapping and overlapping lines allocated randomly in locations, that is, lines appearing in some locations but not in all. In this study we propose using incomplete block designs (IBD), principally, for the allocation of lines to locations in such a way that not all lines are observed in all locations. We compare this allocation with a random allocation of lines to locations guaranteeing that the lines are allocated to

the same number of locations as under the IBD design. We implemented this benchmarking on several crop data sets under the Bayesian genomic best linear unbiased predictor (GBLUP) model, finding that allocation under the principle of IBD outperformed random allocation by between 1.4% and 26.5% across locations, traits, and data sets in terms of mean square error. Although a wide range of performance improvements were observed, our results provide evidence that using IBD for the allocation of lines to locations can help improve predictive performance compared with random allocation. This has the potential to be applied to large-scale plant breeding programs.

Article

CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA Bayes Theorem Genome Inflammatory Bowel Diseases Models, Genetic Plant Breeding

Big data, small explanatory and predictive power: Lessons from random forest modeling of on-farm yield variability and implications for data-driven agronomy

Martin van Ittersum (2023)

Context: Collection and analysis of large volumes of on-farm production data are widely seen as key to understanding yield variability among farmers and improving resource-use efficiency. Objective: The aim of this study was to assess the performance of statistical and machine learning methods to explain and predict crop yield across thousands of farmers’ fields in contrasting farming systems worldwide. Methods: A large database of 10,940 field-year combinations from three countries in different stages of agricultural intensification was analyzed. Random effects models were used to partition crop yield variability and random forest models were used to explain and predict crop yield within a cross-validation scheme with data re-sampling over space and time. Results: Yield variability in relative terms was smallest for wheat and barley in the Netherlands and for wheat in Ethiopia, intermediate for rice in the Philippines, and greatest for maize in Ethiopia. Random forest models comprising a total of 87 variables explained a maximum of 65 % of cereal yield variability in the Netherlands and less than 45 % of cereal yield variability in Ethiopia and in the Philippines. Crop management related variables were important to explain and predict cereal yields in Ethiopia, while predictive (i.e., known before the growing season) climatic variables and explanatory (i.e., known during or after the growing season) climatic variables were most important to explain and predict cereal yield variability in the Philippines and in the Netherlands, respectively. Finally, model cross-validation for regions or years not seen during model training reduced the R2 considerably for most crop x country combinations, while for wheat in the Netherlands this was model dependent. Conclusion: Big data from farmers’ fields is useful to explain on-farm yield variability to some extent, but not to predict it across time and space. Significance: The results call for moderate expectations towards big data and machine learning in agronomic studies, particularly for smallholder farms in the tropics where model performance was poorest independently of the variables considered and the cross-validation scheme used.

Article

Model Accuracy Model Precision Linear Mixed Models CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MACHINE LEARNING SUSTAINABLE INTENSIFICATION BIG DATA YIELDS MODELS AGRONOMY

Análisis preventivos de variables para la industria cerámica con base en la metodología de análisis a modo y efecto de falla (FMEA method)

Preventive analysis of variables for the ceramic industry based on the failure mode and effect analysis (FMEA method)

Rigel Hugo Carreón Reyes Juan Carlos Neri Guzmán (2023)

El presente estudio indica de una forma tangible la aplicación de la herramienta FMEA (Failure Mode And Effects Analysis -por sus siglas en inglés) en la aplicación de fabricación de cerámica sanitaria, en donde se evalúan las variables que están relacionadas con el proceso de diseño, procesamiento de piezas cerámicas y de su relación existente para poder alcanzar los requisitos normativos y que estos a su vez sean alcanzables. Dentro del estudio se presenta el análisis y elaboración de la matriz riesgos en modo de fallas, así como una serie de definiciones estadísticas con las cuales son evaluados los procesos de fabricación, así como la explicación clara de la metodología FMEA en donde se indica la adecuación de estos conceptos a este tipo de manufacturas (cerámica sanitaria). Este trabajo también describe a través del estudio de caso de las variables una metodología que detalla los conceptos básicos tales como severidad, detección y ocurrencia combinando el desarrollo de tablas parametrizadas y / o acopladas al tipo de proceso de manufactura cerámica .En los resultados que se obtienen se observa la disminución de la incertidumbre hasta de 85% en los valores de RPN y una mejora en el cpk >1,33 como índice de calidad los riesgos o incertidumbres disminuidos son de forma numérica a través de la comprobación de nuevas acciones y el reanálisis de los conceptos de ocurrencia y detección derivados de la implementación de acciones. Las conclusiones indican como una herramienta adecuada el uso de FMEA para el campo de aplicación de la manufactura de cerámica sanitaria.

The present study indicates in a tangible way the application of the FMEA tool (Failure Mode and Effects Analysis) in the application of sanitary ceramic manufacturing, where the variables that are related to the process of design, processing of ceramic pieces and their existing relationship are evaluated in order to achieve the regulatory requirements and that these in turn are achievable. The study presents the analysis and elaboration of the risk matrix in failure mode as well as a series of statistical definitions with which the manufacturing processes are evaluated as well as the clear explanation of the FMEA methodology (failure mode and effects analysis) where the application and adequacy of these concepts to this type of manufactures (sanitary ceramics) is indicated. This paper also describes through the case study of the variables a methodology that details the basic concepts such as severity, detection and occurrence combining the development of parameterized tables and / or coupled to the type of ceramic manufacturing process. In the results obtained, the decrease in uncertainty of until 85% in the values of RPN and an improvement in the cpk >1.33 as a quality index, the risks or uncertainties decreased are numerically through the verification of new actions and the reanalysis of the concepts of occurrence and detection derived from the implementation of actions. The conclusions indicate as an appropriate tool the use of FMEA for the field of application of the manufacture of sanitary ceramics.

Article

AMEF (Análisis de Modo de Efecto y Falla) Productos cerámicos Cerámica sanitaria Procesos cerámicos Severidad Detección Ocurrencia FMEA (Failure Mode and Effects Analysis) Ceramic products Standard ASME Sanitary ceramic Ceramic processess INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS OTRAS ESPECIALIDADES TECNOLÓGICAS OTRAS OTRAS

On-farm storage loss estimates of maize in Kenya using community survey methods

Hugo De Groote Anani Bruce (2023)

Maize is the most important staple in sub-Saharan Africa (SSA), with highly seasonal production. High storage losses affect food security, but good estimations are lacking. A new method using focus group discussions (FGDs) was tested with 121 communities (1439 farmers, 52% women) in Kenya's six maize-growing zones, to estimate the maize losses to storage pests and analyze farmer practices. As control strategies, half of the farmers used chemical pesticides (49%), while hermetic bags (16%) and botanicals (15%) were also popular. Relative loss from weevils in the long rains was estimated at 23%, in the short rains 18%, and annually 21%. Fewer farmers were affected by the larger grain borer (LGB) than by maize weevils: 42% in the long rainy season and 32% in the short rainy season; losses from LGB were also smaller: 19% in the long season, 17% in the short season, and 18% over the year. Total storage loss, from both species combined, was estimated at 36%, or 671,000 tonnes per year. The greatest losses occur in the humid areas, especially the moist mid-altitudes (56%), and with smaller loss in the drylands (20–23%). Extrapolating the point data and overlaying with the maize production map shows the geographic distribution of the losses, with the most important area found around Lake Victoria. FGDs provide convenient and cheap tools to estimate storage losses in representative communities, but a total loss estimate of 36% is higher than is found in other studies, so its accuracy and framing effects need to be assessed. We conclude that storage pests remain a major problem, especially in western Kenya, and that the use of environmentally friendly technologies such as hermetic storage and botanicals needs more attention, both by the public extension service and private agrodealers.

Article

Larger Grain Borer Maize Weevil CIENCIAS AGROPECUARIAS Y BIOTECNOLOGÍA MAIZE STORAGE LOSSES PESTS SURVEY METHODS

Realidad virtual en fenómenos del espacio interestelar

Antonio Luciano Hernández Padilla (2024)

153 páginas. Maestría en Diseño y Visualización de la Información.

El proyecto es un prototipo que se distribuye en varias etapas y sigue un enfoque de diseño de videojuegos para crear una experiencia de realidad virtual (también conocida como VR Virtual Reality) organizada y coherente. Requiere una fusión de conceptos multidisciplinarios, incluyendo ingeniería, diseño tridimensional y programación, lo que demanda a los profesionales involucrados tener sólidos conocimientos y habilidades creativas. El diseño de videojuegos se valora como un proceso que exige dedicación y pasión, aunque también se destaca la importancia de establecer reglas y géneros para orientar el desarrollo del juego. En este proyecto, el juego se clasifica como una aventura en primera persona centrada en la exploración del espacio interestelar, donde el jugador debe seguir reglas preestablecidas para alcanzar objetivos. La ludología, como estudio académico de los juegos, resalta la constante esencia de jugar, aprender y socializar en los juegos. La construcción del mundo del juego se basa en un Game Design Document que describe la visión, género y objetivos del juego. "Space Travel" se centra en la exploración espacial y cuenta con una nave espacial minimalista y un exoplaneta rocoso y gélido. Las mecánicas del juego se centran en la recolección de objetos y su activación, con reglas que guían la interacción del jugador con el entorno. Este proyecto busca ofrecer una experiencia de VR inmersiva y atractiva, centrada en el usuario. El enfoque en los principios de diseño de videojuegos y la planificación a través del Game Design Document demuestran un compromiso con la creación de una experiencia gratificante y significativa. La atención a la inmersión y las mecánicas de juego respaldan la afirmación de que es un desarrollo centrado en la experiencia del usuario.

The ongoing project is a prototype in various stages, following a game design approach to create an organized and coherent virtual reality experience. It requires a fusion of multidisciplinary concepts, including engineering, three-dimensional design, and programming, demanding that involved professionals possess strong knowledge and creative skills. Game design is valued as a process that demands dedication and passion, while also emphasizing the importance of establishing rules and genres to guide game development. In this project, the game is classified as a first-person adventure focused on interstellar space exploration, where the player must adhere to preset rules to achieve objectives. Ludology, as an academic study of games, highlights the constant essence of playing, learning, and socializing within games. The construction of the game world is based on a Game Design Document describing the vision, genre, and objectives of the game. "Space Travel" focuses on space exploration, featuring a minimalist spaceship and an icy, rocky exoplanet. Game mechanics revolve around object collection and activation, with rules guiding the player's interaction with the environment. This project aims to deliver an immersive and engaging virtual reality experience centered on the user. The focus on game design principles and planning through the Game Design Document demonstrates a commitment to creating a rewarding and meaningful experience. Attention to immersion and game mechanics supports the assertion that it's a user experience focused development.

Master thesis

Espacio, realidad, virtual, interactividad, diseño, experiencia, usuario. Space, Virtual, Reality, interactivity, design, user, experience. Video games--Design. Outer space--Exploration. Video games--Programming. VRML (Computer program language) Three-dimensional display systems. Videojuegos -- Diseño. Espacio exterior -- Exploración. Diseño de sistemas centrado en el usuario. QA76.76.C672 INGENIERÍA Y TECNOLOGÍA CIENCIAS TECNOLÓGICAS TECNOLOGÍA DE LOS ORDENADORES DISEÑO CON AYUDA DE ORDENADOR